Update app.py

app.py

@@ -49,8 +49,8 @@ def inference(query):
     outputs = model.generate(tokenized_chat, **generation_params)
     decoded_outputs = tokenizer.batch_decode(outputs, skip_special_tokens=False)
     assistant_response = decoded_outputs[0].split("<|im_start|>assistant\n")[-1].strip()
-    # response_ = assistant_response.replace('<|im_end|>', "")
-    return assistant_response
+    response_ = assistant_response.replace('<|im_end|>', "")
+    return response_
     # outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)
     # return outputs
 
@@ -63,7 +63,8 @@ examples = ['How can options strategies such as straddles, strangles, and spread
 
 def response(message, history):
     text = inference(message)
-    for i in range(len(text)):
-        time.sleep(0.01)
-        yield text[: i + 1]
+    return text 
+    # for i in range(len(text)):
+    #     time.sleep(0.01)
+    #     yield text[: i + 1]
 gr.ChatInterface(response,examples=examples).launch()